Yiqing Liang

Yiqing Liang, Eliot Laidlaw, Alexander Meyerowitz et al. · stanford

From video, we reconstruct a neural volume that captures time-varying color, density, scene flow, semantics, and attention information. The semantics and attention let us identify salient foreground objects separately from the background across spacetime. To mitigate low resolution semantic and attention features, we compute pyramids that trade detail with whole-image context. After optimization, we perform a saliency-aware clustering to decompose the scene. To evaluate real-world scenes, we annotate object masks in the NVIDIA Dynamic Scene and DyCheck datasets. We demonstrate that this method can decompose dynamic scenes in an unsupervised way with competitive performance to a supervised method, and that it improves foreground/background segmentation over recent static/dynamic split methods. Project Webpage: https://visual.cs.brown.edu/saff

Tianye Ding, Yiming Xie, Yiqing Liang et al.

Recent feed-forward reconstruction models like VGGT and $π^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming methods address this through learned memory mechanisms or causal attention, they require extensive retraining and may not fully leverage the strong geometric priors of state-of-the-art offline models. We propose LASER, a training-free framework that converts an offline reconstruction model into a streaming system by aligning predictions across consecutive temporal windows. We observe that simple similarity transformation ($\mathrm{Sim}(3)$) alignment fails due to layer depth misalignment: monocular scale ambiguity causes relative depth scales of different scene layers to vary inconsistently between windows. To address this, we introduce layer-wise scale alignment, which segments depth predictions into discrete layers, computes per-layer scale factors, and propagates them across both adjacent windows and timestamps. Extensive experiments show that LASER achieves state-of-the-art performance on camera pose estimation and point map reconstruction %quality with offline models while operating at 14 FPS with 6 GB peak memory on a RTX A6000 GPU, enabling practical deployment for kilometer-scale streaming videos. Project website: $\href{https://neu-vi.github.io/LASER/}{\texttt{https://neu-vi.github.io/LASER/}}$

Yiqing Liang, Numair Khan, Zhengqin Li et al.

We propose a method that achieves state-of-the-art rendering quality and efficiency on monocular dynamic scene reconstruction using deformable 3D Gaussians. Implicit deformable representations commonly model motion with a canonical space and time-dependent backward-warping deformation field. Our method, GauFRe, uses a forward-warping deformation to explicitly model non-rigid transformations of scene geometry. Specifically, we propose a template set of 3D Gaussians residing in a canonical space, and a time-dependent forward-warping deformation field to model dynamic objects. Additionally, we tailor a 3D Gaussian-specific static component supported by an inductive bias-aware initialization approach which allows the deformation field to focus on moving scene regions, improving the rendering of complex real-world motion. The differentiable pipeline is optimized end-to-end with a self-supervised rendering loss. Experiments show our method achieves competitive results and higher efficiency than both previous state-of-the-art NeRF and Gaussian-based methods. For real-world scenes, GauFRe can train in ~20 mins and offer 96 FPS real-time rendering on an RTX 3090 GPU. Project website: https://lynl7130.github.io/gaufre/index.html

Yiqing Liang, Jielin Qiu, Wenhao Ding et al. · cmu

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art performance on tasks with structured, verifiable answers. Applying RLVR to Multimodal LLMs (MLLMs) presents significant opportunities but is complicated by the broader, heterogeneous nature of vision-language tasks that demand nuanced visual, logical, and spatial capabilities. As such, training MLLMs using RLVR on multiple datasets could be beneficial but creates challenges with conflicting objectives from interaction among diverse datasets, highlighting the need for optimal dataset mixture strategies to improve generalization and reasoning. We introduce a systematic post-training framework for Multimodal LLM RLVR, featuring a rigorous data mixture problem formulation and benchmark implementation. Specifically, (1) We developed a multimodal RLVR framework for multi-dataset post-training by curating a dataset that contains different verifiable vision-language problems and enabling multi-domain online RL learning with different verifiable rewards; (2) We proposed a data mixture strategy that learns to predict the RL fine-tuning outcome from the data mixture distribution, and consequently optimizes the best mixture. Comprehensive experiments showcase that multi-domain RLVR training, when combined with mixture prediction strategies, can significantly boost MLLM general reasoning capacities. Our best mixture improves the post-trained model's accuracy on out-of-distribution benchmarks by an average of 5.24% compared to the same model post-trained with uniform data mixture, and by a total of 20.74% compared to the pre-finetuning baseline.

Yiqing Liang, Abhishek Badki, Hang Su et al.

Large models have shown generalization across datasets for many low-level vision tasks, like depth estimation, but no such general models exist for scene flow. Even though scene flow has wide potential use, it is not used in practice because current predictive models do not generalize well. We identify three key challenges and propose solutions for each. First, we create a method that jointly estimates geometry and motion for accurate prediction. Second, we alleviate scene flow data scarcity with a data recipe that affords us 1M annotated training samples across diverse synthetic scenes. Third, we evaluate different parameterizations for scene flow prediction and adopt a natural and effective parameterization. Our resulting model outperforms existing methods as well as baselines built on large-scale models in terms of 3D end-point error, and shows zero-shot generalization to the casually captured videos from DAVIS and the robotic manipulation scenes from RoboTAP. Overall, our approach makes scene flow prediction more practical in-the-wild.

Yiqing Liang, Mikhail Okunev, Mikaela Angelina Uy et al.

Gaussian splatting methods are emerging as a popular approach for converting multi-view image data into scene representations that allow view synthesis. In particular, there is interest in enabling view synthesis for dynamic scenes using only monocular input data -- an ill-posed and challenging problem. The fast pace of work in this area has produced multiple simultaneous papers that claim to work best, which cannot all be true. In this work, we organize, benchmark, and analyze many Gaussian-splatting-based methods, providing apples-to-apples comparisons that prior works have lacked. We use multiple existing datasets and a new instructive synthetic dataset designed to isolate factors that affect reconstruction quality. We systematically categorize Gaussian splatting methods into specific motion representation types and quantify how their differences impact performance. Empirically, we find that their rank order is well-defined in synthetic data, but the complexity of real-world data currently overwhelms the differences. Furthermore, the fast rendering speed of all Gaussian-based methods comes at the cost of brittleness in optimization. We summarize our experiments into a list of findings that can help to further progress in this lively problem setting.

Wenyan Cong, Yiqing Liang, Yancheng Zhang et al.

Spatial intelligence, encompassing 3D reconstruction, perception, and reasoning, is fundamental to applications such as robotics, aerial imaging, and extended reality. A key enabler is the real-time, accurate estimation of core 3D attributes (camera parameters, point clouds, depth maps, and 3D point tracks) from unstructured or streaming imagery. Inspired by the success of large foundation models in language and 2D vision, a new class of end-to-end 3D geometric foundation models (GFMs) has emerged, directly predicting dense 3D representations in a single feed-forward pass, eliminating the need for slow or unavailable precomputed camera parameters. Since late 2023, the field has exploded with diverse variants, but systematic evaluation is lacking. In this work, we present the first comprehensive benchmark for 3D GFMs, covering five core tasks: sparse-view depth estimation, video depth estimation, 3D reconstruction, multi-view pose estimation, novel view synthesis, and spanning both standard and challenging out-of-distribution datasets. Our standardized toolkit automates dataset handling, evaluation protocols, and metric computation to ensure fair, reproducible comparisons. We evaluate 16 state-of-the-art GFMs, revealing their strengths and limitations across tasks and domains, and derive key insights to guide future model scaling and optimization. All code, evaluation scripts, and processed data will be publicly released to accelerate research in 3D spatial intelligence.

Lulin Liu, Dayou Li, Yiqing Liang et al.

Large foundation models have made significant advances in embodied intelligence, enabling synthesis and reasoning over egocentric input for household tasks. However, VLM-based auto-labeling is often noisy because the primary data sources lack accurate human action labels, chain-of-thought (CoT), and spatial annotations; these errors are amplified during long-horizon spatial instruction following. These issues stem from insufficient coverage of minute-long, daily household planning tasks and from inaccurate spatial grounding. As a result, VLM reasoning chains and world-model synthesis can hallucinate objects, skip steps, or fail to respect real-world physical attributes. To address these gaps, we introduce EgoTL. EgoTL builds a think-aloud capture pipeline for egocentric data. It uses a say-before-act protocol to record step-by-step goals and spoken reasoning with word-level timestamps, then calibrates physical properties with metric-scale spatial estimators, a memory-bank walkthrough for scene context, and clip-level tags for navigation instructions and detailed manipulation actions. With EgoTL, we are able to benchmark VLMs and World Models on six task dimensions from three layers and long-horizon generation over minute-long sequences across over 100 daily household tasks. We find that foundation models still fall short as egocentric assistants or open-world simulators. Finally, we finetune foundation models with human CoT aligned with metric labels on the training split of EgoTL, which improves long-horizon planning and reasoning, step-wise reasoning, instruction following, and spatial grounding.

Zhecan Wang, Haoxuan You, Liunian Harold Li et al.

Answering complex questions about images is an ambitious goal for machine intelligence, which requires a joint understanding of images, text, and commonsense knowledge, as well as a strong reasoning ability. Recently, multimodal Transformers have made great progress in the task of Visual Commonsense Reasoning (VCR), by jointly understanding visual objects and text tokens through layers of cross-modality attention. However, these approaches do not utilize the rich structure of the scene and the interactions between objects which are essential in answering complex commonsense questions. We propose a Scene Graph Enhanced Image-Text Learning (SGEITL) framework to incorporate visual scene graphs in commonsense reasoning. To exploit the scene graph structure, at the model structure level, we propose a multihop graph transformer for regularizing attention interaction among hops. As for pre-training, a scene-graph-aware pre-training method is proposed to leverage structure knowledge extracted in the visual scene graph. Moreover, we introduce a method to train and generate domain-relevant visual scene graphs using textual annotations in a weakly-supervised manner. Extensive experiments on VCR and other tasks show a significant performance boost compared with the state-of-the-art methods and prove the efficacy of each proposed component.

Yiqing Liang, Boyuan Chen, Shuran Song

This paper focuses on visual semantic navigation, the task of producing actions for an active agent to navigate to a specified target object category in an unknown environment. To complete this task, the algorithm should simultaneously locate and navigate to an instance of the category. In comparison to the traditional point goal navigation, this task requires the agent to have a stronger contextual prior to indoor environments. We introduce SSCNav, an algorithm that explicitly models scene priors using a confidence-aware semantic scene completion module to complete the scene and guide the agent's navigation planning. Given a partial observation of the environment, SSCNav first infers a complete scene representation with semantic labels for the unobserved scene together with a confidence map associated with its own prediction. Then, a policy network infers the action from the scene completion result and confidence map. Our experiments demonstrate that the proposed scene completion module improves the efficiency of the downstream navigation policies. Video, code, and data: https://sscnav.cs.columbia.edu/